CN110604616A - Interventional operation path planning method and system based on graph search and electronic equipment - Google Patents
Interventional operation path planning method and system based on graph search and electronic equipment Download PDFInfo
- Publication number
- CN110604616A CN110604616A CN201910853457.XA CN201910853457A CN110604616A CN 110604616 A CN110604616 A CN 110604616A CN 201910853457 A CN201910853457 A CN 201910853457A CN 110604616 A CN110604616 A CN 110604616A
- Authority
- CN
- China
- Prior art keywords
- graph
- path
- blood vessel
- point
- points
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 79
- 210000004204 blood vessel Anatomy 0.000 claims abstract description 112
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 45
- 238000010845 search algorithm Methods 0.000 claims abstract description 28
- 230000008569 process Effects 0.000 claims description 26
- 230000002792 vascular Effects 0.000 claims description 21
- 238000004364 calculation method Methods 0.000 claims description 20
- 230000015654 memory Effects 0.000 claims description 15
- 239000011159 matrix material Substances 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000013152 interventional procedure Methods 0.000 claims description 7
- 238000005457 optimization Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 5
- 238000001356 surgical procedure Methods 0.000 claims 2
- 238000010586 diagram Methods 0.000 description 16
- 238000005070 sampling Methods 0.000 description 14
- 238000004088 simulation Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 239000003086 colorant Substances 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003016 pheromone Substances 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B34/00—Computer-aided surgery; Manipulators or robots specially adapted for use in surgery
- A61B34/10—Computer-aided planning, simulation or modelling of surgical operations
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B34/00—Computer-aided surgery; Manipulators or robots specially adapted for use in surgery
- A61B34/10—Computer-aided planning, simulation or modelling of surgical operations
- A61B2034/101—Computer-aided simulation of surgical operations
- A61B2034/105—Modelling of the patient, e.g. for ligaments or bones
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B34/00—Computer-aided surgery; Manipulators or robots specially adapted for use in surgery
- A61B34/10—Computer-aided planning, simulation or modelling of surgical operations
- A61B2034/107—Visualisation of planned trajectories or target regions
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B34/00—Computer-aided surgery; Manipulators or robots specially adapted for use in surgery
- A61B34/10—Computer-aided planning, simulation or modelling of surgical operations
- A61B2034/108—Computer aided selection or customisation of medical implants or cutting guides
Landscapes
- Health & Medical Sciences (AREA)
- Surgery (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Robotics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The application relates to an interventional operation path planning method, an interventional operation path planning system and electronic equipment based on graph search. The method comprises the following steps: step a: acquiring a three-dimensional image and central line data of a blood vessel; step b: constructing a global graph of a blood vessel topological structure by adopting a graph theory algorithm based on the three-dimensional image and the central line data of the blood vessel; step c: simplifying the global graph to obtain a sparse graph based on the global graph; step d: and performing path search on the sparse graph through a path search algorithm to obtain an optimal path between an intervention starting point and a target position, and taking the optimal path as a blood vessel intervention operation path. The method and the device greatly reduce the calculated amount of the path search algorithm, improve the forming speed of the interventional operation planning method and obviously improve the success rate of the interventional operation.
Description
Technical Field
The application belongs to the technical field of medical engineering, and particularly relates to an interventional operation path planning method and system based on graph search and an electronic device.
Background
In the process of the vascular intervention operation, because of the numerous vessels in the human body and the very complex topological structure, a doctor needs to select an intervention path between an operation intervention starting point and a target point needing treatment through the topological structure of the vessels in the patient, and the process is called as vascular intervention operation path planning.
Currently, there are methods [ Zhou S, Wang C, Zhang D.New method of vessel center extraction from 3D CT coronary and geographic alignment based on open-snake [ C ]// Iet International Conference on biological Image & Signal Processing. IET,2015 ], [ Zhang F, Lu P, Liu X, et al vascular center extraction of CTA images based on minimal and Bayesian tracking [ C ]// 201710 th International alignment on Image and Signal Processing, biological Engineering and information (CISP-BMEI) IEEE 2017. In the field of vascular interventional surgical path planning, scholars have proposed own planning algorithms, such as those proposed by shanghai university in literature [ alias ] vascular interventional surgical path planning based on improved ant colony algorithm [ J ]. proceedings of shanghai university (nature science edition), 2019 ]. According to the method, on the basis of comprehensively considering the diameter of a catheter, the length of a blood vessel, the minimum diameter, the maximum curvature and the maximum deflection, end node factors are introduced, and a heuristic function and an pheromone updating mechanism in an ant colony algorithm are improved to finally obtain a globally optimal planned path. The method generally selects a blood vessel with a larger caliber to perform the operation without considering other better paths, and the problems of slower planning speed and low accuracy are often caused by high time complexity of an algorithm. Meanwhile, the path planning cannot mark error-prone key positions in the operation so that a doctor or a robot control strategy pays attention.
Disclosure of Invention
The application provides an interventional operation path planning method, system and electronic device based on graph search, and aims to solve at least one of the technical problems in the prior art to a certain extent.
In order to solve the above problems, the present application provides the following technical solutions:
an interventional operation path planning method based on graph search comprises the following steps:
step a: acquiring a three-dimensional image and central line data of a blood vessel;
step b: constructing a global graph of a blood vessel topological structure by adopting a graph theory algorithm based on the three-dimensional image and the central line data of the blood vessel;
step c: simplifying the global graph to obtain a sparse graph based on the global graph;
step d: and performing path search on the sparse graph through a path search algorithm to obtain an optimal path between an intervention starting point and a target position, and taking the optimal path as a blood vessel intervention operation path.
The technical scheme adopted by the embodiment of the application further comprises the following steps: in the step b, the constructing a global map of the vascular topological structure by using the graph theory algorithm specifically includes: firstly, establishing a blood vessel topological structure analysis based on a blood vessel three-dimensional image, representing a central line of a blood vessel structure into a series of points with position coordinates, respectively and sequentially numbering the points according to a position relation, and constructing an n-by-n array, wherein n represents the number of points extracted from the central line; secondly, according to the topological structure of the blood vessel, the connection relation between all the points is represented by 1 and 0, and if the x-th point in the matrix is connected with the y-th point, the numerical values of the x-th row and the y-th column and the numerical values of the y-th row and the x-th column are both 1, the numerical values of the positions without the connection relation are both 0, and the finally obtained array is the global graph.
The technical scheme adopted by the embodiment of the application further comprises the following steps: in the step c, the simplifying the global map to obtain a sparse map based on the global map specifically includes: extracting all end points and branch points in the global graph, and renumbering to form a new array of m by m, wherein m represents the number of the extracted end points and branch points; when a node is connected with the next node through a section of single branch blood vessel, the corresponding position in the sparse graph is marked as 1, the position which is not adjacent to all other nodes is marked as 0, the index in the sparse graph is y, and then y is x-z, wherein z is the number of all the other nodes except the end point and the branch point on the single branch blood vessel before the node.
The technical scheme adopted by the embodiment of the application further comprises the following steps: in the step d, the performing the path search on the sparse graph by using the path search algorithm specifically includes: firstly, obtaining an intervention starting point and a target position from a three-dimensional image of a vascular structure; based on the sparse graph, respectively carrying out weight calculation on each node connected with the intervention starting point from the intervention starting point according to a Dijkstra algorithm, calculating the weight of each node connected with the next point, solving the shortest distance from all other nodes to the intervention starting point according to the weight, searching an optimal point connected with the intervention starting point from the intervention starting point according to the connection relation between the optimal point and the nodes in the sparse graph, taking the searched point as a new starting point, searching the optimal point connected with the searched point until the point of the target position is searched, and obtaining the optimal path between the intervention starting point and the target position through all searched points.
The technical scheme adopted by the embodiment of the application further comprises the following steps: the step d further comprises the following steps: and calculating a potential wrong path and a possibly wrong area in the operation process by using the global map, marking the wrong path and the wrong area, judging whether the guide wire enters the wrong path or the wrong area in the operation process, and reminding a doctor when the guide wire enters the wrong path or the wrong area.
Another technical scheme adopted by the embodiment of the application is as follows: a graph search based interventional surgical path planning system, comprising:
a data acquisition module: the system is used for acquiring a three-dimensional image and central line data of a blood vessel;
a graph building module: the method comprises the steps of constructing a global graph of a blood vessel topological structure by adopting a graph theory algorithm based on the three-dimensional image and the central line data of the blood vessel;
a graph optimization module: the global graph is simplified to obtain a sparse graph based on the global graph;
a path search module: and the method is used for carrying out path search on the sparse graph through a path search algorithm to obtain an optimal path between the intervention starting point and the target position, and taking the optimal path as a blood vessel intervention operation path.
The technical scheme adopted by the embodiment of the application further comprises the following steps: the map construction module adopts a graph theory algorithm to construct a global map of the vascular topological structure, and specifically comprises the following steps: firstly, establishing a blood vessel topological structure analysis based on a blood vessel three-dimensional image, representing a central line of a blood vessel structure into a series of points with position coordinates, respectively and sequentially numbering the points according to a position relation, and constructing an n-by-n array, wherein n represents the number of points extracted from the central line; secondly, according to the topological structure of the blood vessel, the connection relation between all the points is represented by 1 and 0, and if the x-th point in the matrix is connected with the y-th point, the numerical values of the x-th row and the y-th column and the numerical values of the y-th row and the x-th column are both 1, the numerical values of the positions without the connection relation are both 0, and the finally obtained array is the global graph.
The technical scheme adopted by the embodiment of the application further comprises the following steps: the graph optimization module simplifies the global graph to obtain a sparse graph based on the global graph specifically comprises: extracting all end points and branch points in the global graph, and renumbering to form a new array of m by m, wherein m represents the number of the extracted end points and branch points; when a node is connected with the next node through a section of single branch blood vessel, the corresponding position in the sparse graph is marked as 1, the position which is not adjacent to all other nodes is marked as 0, the index in the sparse graph is y, and then y is x-z, wherein z is the number of all the other nodes except the end point and the branch point on the single branch blood vessel before the node.
The technical scheme adopted by the embodiment of the application further comprises the following steps: the path search module performs path search on the sparse graph through a path search algorithm, specifically: firstly, obtaining an intervention starting point and a target position from a three-dimensional image of a vascular structure; based on the sparse graph, respectively carrying out weight calculation on each node connected with the intervention starting point from the intervention starting point according to a Dijkstra algorithm, calculating the weight of each node connected with the next point, solving the shortest distance from all other nodes to the intervention starting point according to the weight, searching an optimal point connected with the intervention starting point from the intervention starting point according to the connection relation between the optimal point and the nodes in the sparse graph, taking the searched point as a new starting point, searching the optimal point connected with the searched point until the point of the target position is searched, and obtaining the optimal path between the intervention starting point and the target position through all searched points.
The technical scheme adopted by the embodiment of the application further comprises a wrong path calculation module, wherein the wrong path calculation module is used for calculating a potential wrong path and a possibly wrong area in the operation process by using the global map, marking the wrong path and the area, judging whether the guide wire enters the wrong path or the wrong area in the operation process, and reminding a doctor when the guide wire enters the wrong path or the wrong area.
The embodiment of the application adopts another technical scheme that: an electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the one processor to cause the at least one processor to perform the following operations of the graph search based interventional surgical path planning method described above:
step a: acquiring a three-dimensional image and central line data of a blood vessel;
step b: constructing a global graph of a blood vessel topological structure by adopting a graph theory algorithm based on the three-dimensional image and the central line data of the blood vessel;
step c: simplifying the global graph to obtain a sparse graph based on the global graph;
step d: and performing path search on the sparse graph through a path search algorithm to obtain an optimal path between an intervention starting point and a target position, and taking the optimal path as a blood vessel intervention operation path.
Compared with the prior art, the embodiment of the application has the advantages that: the interventional operation path planning method, the interventional operation path planning system and the electronic equipment based on the graph search describe the topological structure of the blood vessel three-dimensional image by using a graph theory method through quoting a graph theory algorithm, and improve the path search calculation speed by using a Dijkstra algorithm. In addition, all error paths which can enter the guiding wire in the interventional operation process are selected, meanwhile, all positions which can be mistakenly located in the operation process are marked, whether the guiding wire is wrong or not is judged in real time in the operation process, therefore, a doctor is reminded, the doctor can be reminded of making corresponding adjustment after the error occurs, and the safety of the interventional operation is improved.
Drawings
Fig. 1 is a flowchart of an interventional procedure path planning method based on graph search according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a 3D model of a vessel generated based on a vessel phantom used for simulation and its centerline trajectory;
FIG. 3 is a diagram of a global graph formation;
FIG. 4 is a schematic diagram of a sparse graph structure;
FIG. 5 is a schematic diagram of the positions of important nodes such as vessel center lines and end points and bifurcation points calculated by the global map;
fig. 6 is a schematic structural diagram of an interventional surgical path planning system based on graph search according to an embodiment of the present application;
FIG. 7(a), (b), (c), and (d) are schematic diagrams of different results obtained by selecting different intervention starting points in a simulation experiment, respectively;
fig. 8 is a schematic structural diagram of a hardware device of an interventional operation path planning method based on graph search according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Please refer to fig. 1, which is a flowchart of an interventional operation path planning method based on graph search according to an embodiment of the present application. The interventional operation path planning method based on graph search comprises the following steps:
step 100: acquiring a three-dimensional image and central line data of a blood vessel;
step 200: based on the three-dimensional image and the central line data of the blood vessel, a global graph for describing the topological structure of the blood vessel is constructed by adopting a graph theory algorithm;
in step 200, a 3D model of the vessel generated based on the vessel phantom used for the simulation and its centerline trajectory are shown in fig. 2. The graph construction method specifically comprises the following steps: firstly, establishing a blood vessel topological structure analysis based on a blood vessel three-dimensional image, wherein a central line of a blood vessel structure can be represented as a series of points with position coordinates, the points are respectively numbered according to the position relation in sequence, and an n-by-n array is constructed, wherein n represents the number of points extracted from the central line. Then, according to the topology of the blood vessel, the connection relationship between these points is represented by 1 and 0, and as shown in fig. 3, a diagram is formed for a global diagram. The global graph shown in fig. 3 is made up of a matrix of 404 x 404, 404 being the number of centerline sample points. If the x-th point and the y-th point in the matrix are connected, the value in the x-th row and the y-th column is one, the value in the y-th row and the x-th column is also one, and the positions without connection relations are all filled with 0, and the topological structure of the center line of the blood vessel can be obtained in this way. Thus, all the endpoints in the vascular structure, which have only one 1 on the row, indicate that they are connected to only one point. And all bifurcations in the blood vessel have more than two 1's, indicating that they are connected to at least three points. Only two points on the trunk and branch of all blood vessels except the end points and the bifurcation points have 1, which means that the trunk and the branch have connection relation with only two points in front and at the back. The array that is finally obtained is the global map.
Based on the above, the topological structure of the blood vessel three-dimensional image is described by using a graph theory method by using a graph theory algorithm, and key nodes of the topological structure are classified by using an innovative method, so that the calculation amount of a subsequent path search algorithm is greatly reduced, the speed of path planning of the interventional operation is improved, and the success rate of the interventional operation is remarkably improved.
Step 300: simplifying the global graph, and only keeping the position connection relation of end points and bifurcation points to obtain a sparse graph based on the global graph;
in step 300, in order to speed up the search efficiency of the search algorithm, the present application proposes a sparse graph concept based on a global graph. From the global map, the three-dimensional model can be discarded, and the nature of the point extracted by the centerline can be judged by only calculating the number of 1's on each line, i.e. judging whether the point is a bifurcation point or an end point. In the search algorithm, only the end points and bifurcation points of the vascular structure affect the search results. Therefore, the method extracts all end points and branch points in the global graph, and renumbers the end points and the branch points to form a new array of m by m, wherein m represents the number of the extracted end points and branch points. Similar to the global map, when one node is connected to the next node through a single branch vessel, the corresponding location in the sparse map is labeled with 1, while all other non-adjacent locations are labeled with 0. The index of each point in the global graph is x, the index in the sparse graph is y, and then y is x-z, wherein z is the number of all the nodes except the end point and the branch point on the single blood vessel branch before the node. By the form, the calculation amount of the search algorithm can be greatly reduced, and the effect of describing the topological structure of the blood vessel is achieved. The sparse graph structure is shown in fig. 4. Because the unimportant points in all the topological structures are discarded (only all the end points and all the branch points in the blood vessel structure are reserved), the sparse graph shown in fig. 4 is formed by a matrix of 12 × 12, and 12 is the sum of all the branch points and the end points of the blood vessel phantom, which is greatly simplified compared with the global graph, so that the topological structures of the blood vessels can be described in the simplest way, and a great contribution is made to the improvement of the efficiency of the subsequent search algorithm. In the previous global graph, the vessel number and the sequence between each node can be stored, and used for the weight of each node calculated by the subsequent search algorithm.
Step 400: performing path search on the sparse graph through a Dijkstra algorithm to obtain an optimal path between an intervention starting point and a target position, and taking the optimal path as a blood vessel intervention operation path;
in step 400, dijkstra's algorithm is an algorithm for solving the problem of the shortest path of a single source, and the algorithm is characterized in that the algorithm is expanded from a starting point to an outer layer until the final point is reached. The specific calculation method comprises the following steps: firstly, an intervention starting point and a target position are obtained from a three-dimensional image of a vascular structure. It is possible to directly acquire the position coordinates of the clicked position in the three-dimensional image and acquire the index of the node of the blood vessel center line closest to this position coordinates. Then, based on the sparse graph, respectively calculating the weight of each node connected with the intervention starting point from the intervention starting point according to the Dijkstra algorithm, and then calculating the weight of each node connected with the intervention starting point at the next point. The weights here can be obtained from the number of center sampling points contained in each single blood vessel between nodes, and these data are already stored when the sparse graph is calculated. And the weight is determined according to specific situations by combining factors such as the radius of the blood vessel, the radius of curvature and the like.
Fig. 5 is a schematic diagram showing the positions of important nodes such as the center line of a blood vessel and the end points and bifurcation points calculated by the global graph. Since the radius of the blood vessel shown in the three-dimensional image of the blood vessel in fig. 2 is uniform, and the distance between the sampling points of the center line of the blood vessel is uniform, the weight of each node is represented by the number of the sampling points of the center line from the current position node to the last connected node. Because the optimal path in the interventional procedure under the condition of the same vessel width is the shortest path from the interventional starting point to the target position. The shortest distance from all other nodes to the intervention starting point can be obtained by using Dijksta algorithm, according to the connection relation between the nodes in the sparse graph and the intervention starting point, the optimal point connected with the intervention starting point is searched, the searched point is used as a new starting point, the optimal point connected with the intervention starting point is searched until the point of the target position is searched, and the optimal intervention path can be obtained through the series of searched points. Based on the analysis and classification of the topological structure, the algorithm has high accuracy of searching the optimal path and high calculation speed, and the interactive automatic search of the optimal intervention path can allow a doctor to randomly select any two points on the topological structure to form the optimal path, so that the efficiency of forming an operation plan by the doctor is improved, and the method is greatly helpful for improving the success rate of the intervention operation.
Step 500: calculating all potential wrong paths and regions which are possibly wrong in the operation process by using the global map, marking the wrong paths and regions, automatically judging whether the guide wire enters the wrong paths or regions in the operation process, and carrying out wrong reminding on a doctor when the guide wire enters the wrong paths or regions so as to complete the planning of the whole blood vessel interventional operation path;
in step 500, the method for calculating the error path specifically includes: firstly, judging whether the point is a bifurcation point according to the number of positions with the value of 1 on each line in the global graph, and regarding the point as the bifurcation point only when the number with the value of 1 is more than or equal to three. And finding out all points adjacent to the bifurcation point according to the column where the position with the value of 1 in the row of the bifurcation point in the global graph is located. Therefore, all the bifurcation points and all the center line sampling points passed by the optimal path can be found out firstly, and the overlapped part, namely all the bifurcation points passed by the optimal path, can be found out. Then all points adjacent to the bifurcation points are found, and all points which pass through the sampling point of the central line in the optimal path are screened out, so that the starting point of all paths which can be wrong in the interventional operation process is obtained. The global graph is then used to find the next point (centerline sample point) adjacent to the starting point of these wrong paths and traversed until reaching other nodes. And marking the optimal path, the error path and the error area by adopting line segments with different colors in the global graph.
For convenience of explanation, in the embodiment of the present application, red line segments are respectively used to mark an optimal path in an intervention process, blue line segments are used to indicate a potential wrong path in the intervention process, green line segments are used to mark an area where a guidewire may be wrong in the intervention process, 20mm is selected as a data acquisition length for judging whether to enter the wrong path, a bifurcation point where all optimal paths pass is marked by a green line segment to each path adjacent to the bifurcation point, the length of each line segment is 20mm, and the specific length can also be set according to actual operation. When the magnetic positioning data are collected, if the magnetic positioning points enter the green line segment marking area, the error average of the positioning points and the blue line segment and the error average of the positioning points and the red line segment are respectively calculated. W1 is h1/N, W2 is h2/N, where h1 and h2 respectively represent the sum of errors of the positioning points and the centerline sampling points corresponding to the blue line segment and the sum of errors of the positioning points and the centerline sampling points corresponding to the red line segment, N represents the number of the positioning points, and W1 and W2 respectively represent average errors of the positioning points and the centerline sampling points corresponding to the red line segment. When the former value is smaller than the latter value, the guide wire is judged to enter an incorrect path or area, and a corresponding signal is fed back to a doctor or a control system of the robot, so that the safety of the interventional operation is ensured.
Please refer to fig. 6, which is a schematic structural diagram of an interventional operation path planning system based on graph search according to an embodiment of the present application. The interventional operation path planning system based on graph search comprises a data acquisition module, a graph construction module, a graph optimization module, a path search module and an error path calculation module.
A data acquisition module: the system is used for acquiring a three-dimensional image and central line data of a blood vessel;
a graph building module: the method comprises the steps that a global graph used for describing a topological structure of a blood vessel is constructed by adopting a graph theory algorithm based on three-dimensional images and central line data of the blood vessel; wherein the 3D model of the vessel generated based on the vessel phantom used for the simulation and its centerline trajectory are shown in fig. 2. The graph construction method specifically comprises the following steps: firstly, establishing a blood vessel topological structure analysis based on a blood vessel three-dimensional image, wherein a central line of a blood vessel structure can be represented as a series of points with position coordinates, the points are respectively numbered according to the position relation in sequence, and an n-by-n array is constructed, wherein n represents the number of points extracted from the central line. Then, according to the topology of the blood vessel, the connection relationship between these points is represented by 1 and 0, and as shown in fig. 3, a diagram is formed for a global diagram. The global graph shown in fig. 3 is made up of a matrix of 404 x 404, 404 being the number of centerline sample points. If the x-th point and the y-th point in the matrix are connected, the value in the x-th row and the y-th column is one, the value in the y-th row and the x-th column is also one, and the positions without connection relations are all filled with 0, and the topological structure of the center line of the blood vessel can be obtained in this way. Thus, all the endpoints in the vascular structure, which have only one 1 on the row, indicate that they are connected to only one point. And all bifurcations in the blood vessel have more than two 1's, indicating that they are connected to at least three points. Only two points on the trunk and branch of all blood vessels except the end points and the bifurcation points have 1, which means that the trunk and the branch have connection relation with only two points in front and at the back. The array that is finally obtained is the global map.
Based on the above, the topological structure of the blood vessel three-dimensional image is described by using a graph theory method by using a graph theory algorithm, and key nodes of the topological structure are classified by using an innovative method, so that the calculation amount of a subsequent path search algorithm is greatly reduced, the speed of path planning of the interventional operation is improved, and the success rate of the interventional operation is remarkably improved.
A graph optimization module: the method comprises the steps of simplifying a global graph, and only keeping the position connection relation of end points and bifurcation points to obtain a sparse graph based on the global graph; in order to accelerate the search efficiency of a search algorithm, a sparse graph concept based on a global graph is provided. From the global map, the three-dimensional model can be discarded, and the nature of the point extracted by the centerline can be judged by only calculating the number of 1's on each line, i.e. judging whether the point is a bifurcation point or an end point. In the search algorithm, only the end points and bifurcation points of the vascular structure affect the search results. Therefore, the method extracts all end points and branch points in the global graph, and renumbers the end points and the branch points to form a new array of m by m, wherein m represents the number of the extracted end points and branch points. Similar to the global map, when one node is connected to the next node through a single branch vessel, the corresponding location in the sparse map is labeled with 1, while all other non-adjacent locations are labeled with 0. The index of each point in the global graph is x, the index in the sparse graph is y, and then y is x-z, wherein z is the number of all the nodes except the end point and the branch point on the single blood vessel branch before the node. By the form, the calculation amount of the search algorithm can be greatly reduced, and the effect of describing the topological structure of the blood vessel is achieved. The sparse graph structure is shown in fig. 4. Because the unimportant points in all the topological structures are discarded (only all the end points and all the branch points in the blood vessel structure are reserved), the sparse graph shown in fig. 4 is formed by a matrix of 12 × 12, and 12 is the sum of all the branch points and the end points of the blood vessel phantom, which is greatly simplified compared with the global graph, so that the topological structures of the blood vessels can be described in the simplest way, and a great contribution is made to the improvement of the efficiency of the subsequent search algorithm. In the previous global graph, the vessel number and the sequence between each node can be stored, and used for the weight of each node calculated by the subsequent search algorithm.
A path search module: the method comprises the steps of performing path search on a sparse graph through a Dijkstra algorithm to obtain an optimal path between an intervention starting point and a target position, and taking the optimal path as a blood vessel intervention operation path; the Dijkstra algorithm is an algorithm for solving the problem of the shortest path of a single source, and is characterized in that the algorithm is expanded from a starting point to an outer layer by layer until a final point is reached. The specific calculation method comprises the following steps: firstly, an intervention starting point and a target position are obtained from a three-dimensional image of a vascular structure. It is possible to directly acquire the position coordinates of the clicked position in the three-dimensional image and acquire the index of the node of the blood vessel center line closest to this position coordinates. Then, based on the sparse graph, respectively calculating the weight of each node connected with the intervention starting point from the intervention starting point according to the Dijkstra algorithm, and then calculating the weight of each node connected with the intervention starting point at the next point. The weights here can be obtained from the number of center sampling points contained in each single blood vessel between nodes, and these data are already stored when the sparse graph is calculated. And the weight is determined according to specific situations by combining factors such as the radius of the blood vessel, the radius of curvature and the like.
The shortest distance from all other nodes to the intervention starting point can be obtained by using Dijksta algorithm, according to the connection relation between the nodes in the sparse graph and the intervention starting point, the optimal point connected with the intervention starting point is searched, the searched point is used as a new starting point, the optimal point connected with the intervention starting point is searched until the point of the target position is searched, and the optimal intervention path can be obtained through the series of searched points. Based on the analysis and classification of the topological structure, the algorithm has high accuracy of searching the optimal path and high calculation speed, and the interactive automatic search of the optimal intervention path can allow a doctor to randomly select any two points on the topological structure to form the optimal path, so that the efficiency of forming an operation plan by the doctor is improved, and the method is greatly helpful for improving the success rate of the intervention operation.
An error path calculation module: the global graph is used for calculating all potential wrong paths and regions which are possibly wrong in the operation process, marking the wrong paths and regions, automatically judging whether the guide wire enters the wrong paths or regions in the operation process, and carrying out error reminding on a doctor when the guide wire enters the wrong paths or regions so as to complete the planning of the whole blood vessel intervention operation path; the method for calculating the error path specifically comprises the following steps: firstly, judging whether the point is a bifurcation point according to the number of positions with the value of 1 on each line in the global graph, and regarding the point as the bifurcation point only when the number with the value of 1 is more than or equal to three. And finding out all points adjacent to the bifurcation point according to the column where the position with the value of 1 in the row of the bifurcation point in the global graph is located. Therefore, all the bifurcation points and all the center line sampling points passed by the optimal path can be found out firstly, and the overlapped part, namely all the bifurcation points passed by the optimal path, can be found out. Then all points adjacent to the bifurcation points are found, and all points which pass through the sampling point of the central line in the optimal path are screened out, so that the starting point of all paths which can be wrong in the interventional operation process is obtained. The global graph is then used to find the next point (centerline sample point) adjacent to the starting point of these wrong paths and traversed until reaching other nodes. And marking the optimal path, the error path and the error area by adopting line segments with different colors in the global graph.
For convenience of explanation, in the embodiment of the present application, red line segments are respectively used to mark an optimal path in an intervention process, blue line segments are used to indicate a potential wrong path in the intervention process, green line segments are used to mark an area where a guidewire may be wrong in the intervention process, 20mm is selected as a data acquisition length for judging whether to enter the wrong path, a bifurcation point where all optimal paths pass is marked by a green line segment to each path adjacent to the bifurcation point, the length of each line segment is 20mm, and the specific length can also be set according to actual operation. When the magnetic positioning data are collected, if the magnetic positioning points enter the green line segment marking area, the error average of the positioning points and the blue line segment and the error average of the positioning points and the red line segment are respectively calculated. W1 is h1/N, W2 is h2/N, where h1 and h2 respectively represent the sum of errors of the positioning points and the centerline sampling points corresponding to the blue line segment and the sum of errors of the positioning points and the centerline sampling points corresponding to the red line segment, N represents the number of the positioning points, and W1 and W2 respectively represent average errors of the positioning points and the centerline sampling points corresponding to the red line segment. When the former value is smaller than the latter value, the guide wire is judged to enter an incorrect path or area, and a corresponding signal is fed back to a doctor or a control system of the robot, so that the safety of the interventional operation is ensured.
To verify the feasibility and effectiveness of the application, a set of vascular phantom data was used, its three-dimensional images and centerline-related data were collected, and simulation experiments were performed using python with corresponding programming. Specifically, as shown in fig. 7(a), (b), (c), and (d), different results are obtained by selecting different intervention starting points in the simulation experiment. As can be seen from fig. 7(a), if the diagram position is selected as the intervention starting point and the marked position in the diagram is taken as the target position, the automatically generated optimal intervention path from the intervention starting point to the target position is shown as a red line. All blue lines indicate the wrong path that may be entered in the selected optimal intervention path. All green segments represent a range of motion in which the guidewire may enter the wrong path during the interventional procedure. When the guidewire comes near the green line, the system will alert the physician. Fig. 7(b), (c) and (d) show the marked path plans and key parameters of the system when other points are selected as the entry points.
It can be understood that the method is also applicable to other three-dimensional pipeline models similar to complex vascular structures, as long as the three-dimensional images and the central lines of the pipeline models can be obtained, the method can be used for obtaining the global graph and the sparse graph of the pipeline structure, and the optimal path between any two points in the pipeline can be obtained by adopting a path search algorithm.
Fig. 8 is a schematic structural diagram of a hardware device of an interventional operation path planning method based on graph search according to an embodiment of the present application. As shown in fig. 8, the device includes one or more processors and memory. Taking a processor as an example, the apparatus may further include: an input system and an output system.
The processor, memory, input system, and output system may be connected by a bus or other means, as exemplified by the bus connection in fig. 8.
The memory, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules. The processor executes various functional applications and data processing of the electronic device, i.e., implements the processing method of the above-described method embodiment, by executing the non-transitory software program, instructions and modules stored in the memory.
The memory may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data and the like. Further, the memory may include high speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes memory located remotely from the processor, and these remote memories may be connected to the processing system over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input system may receive input numeric or character information and generate a signal input. The output system may include a display device such as a display screen.
The one or more modules are stored in the memory and, when executed by the one or more processors, perform the following for any of the above method embodiments:
step a: acquiring a three-dimensional image and central line data of a blood vessel;
step b: constructing a global graph of a blood vessel topological structure by adopting a graph theory algorithm based on the three-dimensional image and the central line data of the blood vessel;
step c: simplifying the global graph to obtain a sparse graph based on the global graph;
step d: and performing path search on the sparse graph through a path search algorithm to obtain an optimal path between an intervention starting point and a target position, and taking the optimal path as a blood vessel intervention operation path.
The product can execute the method provided by the embodiment of the application, and has the corresponding functional modules and beneficial effects of the execution method. For technical details that are not described in detail in this embodiment, reference may be made to the methods provided in the embodiments of the present application.
Embodiments of the present application provide a non-transitory (non-volatile) computer storage medium having stored thereon computer-executable instructions that may perform the following operations:
step a: acquiring a three-dimensional image and central line data of a blood vessel;
step b: constructing a global graph of a blood vessel topological structure by adopting a graph theory algorithm based on the three-dimensional image and the central line data of the blood vessel;
step c: simplifying the global graph to obtain a sparse graph based on the global graph;
step d: and performing path search on the sparse graph through a path search algorithm to obtain an optimal path between an intervention starting point and a target position, and taking the optimal path as a blood vessel intervention operation path.
Embodiments of the present application provide a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions that, when executed by a computer, cause the computer to perform the following:
step a: acquiring a three-dimensional image and central line data of a blood vessel;
step b: constructing a global graph of a blood vessel topological structure by adopting a graph theory algorithm based on the three-dimensional image and the central line data of the blood vessel;
step c: simplifying the global graph to obtain a sparse graph based on the global graph;
step d: and performing path search on the sparse graph through a path search algorithm to obtain an optimal path between an intervention starting point and a target position, and taking the optimal path as a blood vessel intervention operation path.
The interventional operation path planning method, the interventional operation path planning system and the electronic equipment based on the graph search describe the topological structure of the blood vessel three-dimensional image by using a graph theory method through quoting a graph theory algorithm, and improve the path search calculation speed by using a Dijkstra algorithm. In addition, all error paths which can enter the guiding wire in the interventional operation process are selected, meanwhile, all positions which can be mistakenly located in the operation process are marked, whether the guiding wire is wrong or not is judged in real time in the operation process, therefore, a doctor is reminded, the doctor can be reminded of making corresponding adjustment after the error occurs, and the safety of the interventional operation is improved.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (11)
1. An interventional operation path planning method based on graph search is characterized by comprising the following steps:
step a: acquiring a three-dimensional image and central line data of a blood vessel;
step b: constructing a global graph of a blood vessel topological structure by adopting a graph theory algorithm based on the three-dimensional image and the central line data of the blood vessel;
step c: simplifying the global graph to obtain a sparse graph based on the global graph;
step d: and performing path search on the sparse graph through a path search algorithm to obtain an optimal path between an intervention starting point and a target position, and taking the optimal path as a blood vessel intervention operation path.
2. The method for planning a graph search-based interventional procedure path according to claim 1, wherein in the step b, the constructing the global graph of the vascular topology by using the graph theory algorithm specifically comprises: firstly, establishing a blood vessel topological structure analysis based on a blood vessel three-dimensional image, representing a central line of a blood vessel structure into a series of points with position coordinates, respectively and sequentially numbering the points according to a position relation, and constructing an n-by-n array, wherein n represents the number of points extracted from the central line; secondly, according to the topological structure of the blood vessel, the connection relation between all the points is represented by 1 and 0, and if the x-th point in the matrix is connected with the y-th point, the numerical values of the x-th row and the y-th column and the numerical values of the y-th row and the x-th column are both 1, the numerical values of the positions without the connection relation are both 0, and the finally obtained array is the global graph.
3. The method for planning an interventional procedure based on graph search according to claim 2, wherein in the step c, the simplifying the global graph to obtain the sparse graph based on the global graph specifically comprises: extracting all end points and branch points in the global graph, and renumbering to form a new array of m by m, wherein m represents the number of the extracted end points and branch points; when a node is connected with the next node through a section of single branch blood vessel, the corresponding position in the sparse graph is marked as 1, the position which is not adjacent to all other nodes is marked as 0, the index in the sparse graph is y, and then y is x-z, wherein z is the number of all the other nodes except the end point and the branch point on the single branch blood vessel before the node.
4. The method for planning a path for an interventional operation based on graph search according to any one of claims 1 to 3, wherein in the step d, the path search of the sparse graph by the path search algorithm is specifically: firstly, obtaining an intervention starting point and a target position from a three-dimensional image of a vascular structure; based on the sparse graph, respectively carrying out weight calculation on each node connected with the intervention starting point from the intervention starting point according to a Dijkstra algorithm, calculating the weight of each node connected with the next point, solving the shortest distance from all other nodes to the intervention starting point according to the weight, searching an optimal point connected with the intervention starting point from the intervention starting point according to the connection relation between the optimal point and the nodes in the sparse graph, taking the searched point as a new starting point, searching the optimal point connected with the searched point until the point of the target position is searched, and obtaining the optimal path between the intervention starting point and the target position through all searched points.
5. The map search based interventional surgical path planning method of claim 4, wherein the step d further comprises: and calculating a potential wrong path and a possibly wrong area in the operation process by using the global map, marking the wrong path and the wrong area, judging whether the guide wire enters the wrong path or the wrong area in the operation process, and reminding a doctor when the guide wire enters the wrong path or the wrong area.
6. An interventional procedure path planning system based on graph search, comprising:
a data acquisition module: the system is used for acquiring a three-dimensional image and central line data of a blood vessel;
a graph building module: the method comprises the steps of constructing a global graph of a blood vessel topological structure by adopting a graph theory algorithm based on the three-dimensional image and the central line data of the blood vessel;
a graph optimization module: the global graph is simplified to obtain a sparse graph based on the global graph;
a path search module: and the method is used for carrying out path search on the sparse graph through a path search algorithm to obtain an optimal path between the intervention starting point and the target position, and taking the optimal path as a blood vessel intervention operation path.
7. The system for map search-based interventional surgical path planning according to claim 6, wherein the map construction module employs a graph theory algorithm to construct the global map of the vascular topology specifically comprises: firstly, establishing a blood vessel topological structure analysis based on a blood vessel three-dimensional image, representing a central line of a blood vessel structure into a series of points with position coordinates, respectively and sequentially numbering the points according to a position relation, and constructing an n-by-n array, wherein n represents the number of points extracted from the central line; secondly, according to the topological structure of the blood vessel, the connection relation between all the points is represented by 1 and 0, and if the x-th point in the matrix is connected with the y-th point, the numerical values of the x-th row and the y-th column and the numerical values of the y-th row and the x-th column are both 1, the numerical values of the positions without the connection relation are both 0, and the finally obtained array is the global graph.
8. The system for planning an interventional procedure based on graph search according to claim 7, wherein the graph optimization module simplifies the global graph to obtain a sparse graph based on the global graph specifically comprises: extracting all end points and branch points in the global graph, and renumbering to form a new array of m by m, wherein m represents the number of the extracted end points and branch points; when a node is connected with the next node through a section of single branch blood vessel, the corresponding position in the sparse graph is marked as 1, the position which is not adjacent to all other nodes is marked as 0, the index in the sparse graph is y, and then y is x-z, wherein z is the number of all the other nodes except the end point and the branch point on the single branch blood vessel before the node.
9. The map search based interventional surgical path planning system of any one of claims 6 to 8, wherein the path search module performs the path search on the sparse map through a path search algorithm specifically as follows: firstly, obtaining an intervention starting point and a target position from a three-dimensional image of a vascular structure; based on the sparse graph, respectively carrying out weight calculation on each node connected with the intervention starting point from the intervention starting point according to a Dijkstra algorithm, calculating the weight of each node connected with the next point, solving the shortest distance from all other nodes to the intervention starting point according to the weight, searching an optimal point connected with the intervention starting point from the intervention starting point according to the connection relation between the optimal point and the nodes in the sparse graph, taking the searched point as a new starting point, searching the optimal point connected with the searched point until the point of the target position is searched, and obtaining the optimal path between the intervention starting point and the target position through all searched points.
10. The interventional surgical path planning system based on graph search according to claim 9, further comprising a wrong path calculation module, wherein the wrong path calculation module is configured to calculate a potential wrong path and a possibly wrong region in a surgical procedure by using the global graph, mark the wrong path and the wrong region, determine whether a guide wire enters the wrong path or the wrong region in the surgical procedure, and remind a doctor when the wrong path or the wrong region is entered.
11. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the following operations of the graph search based interventional surgical path planning method of any one of claims 1 to 5 above:
step a: acquiring a three-dimensional image and central line data of a blood vessel;
step b: constructing a global graph of a blood vessel topological structure by adopting a graph theory algorithm based on the three-dimensional image and the central line data of the blood vessel;
step c: simplifying the global graph to obtain a sparse graph based on the global graph;
step d: and performing path search on the sparse graph through a path search algorithm to obtain an optimal path between an intervention starting point and a target position, and taking the optimal path as a blood vessel intervention operation path.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910853457.XA CN110604616B (en) | 2019-09-10 | 2019-09-10 | Interventional operation path planning method and system based on graph search and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910853457.XA CN110604616B (en) | 2019-09-10 | 2019-09-10 | Interventional operation path planning method and system based on graph search and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110604616A true CN110604616A (en) | 2019-12-24 |
| CN110604616B CN110604616B (en) | 2020-12-11 |
Family
ID=68891130
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910853457.XA Active CN110604616B (en) | 2019-09-10 | 2019-09-10 | Interventional operation path planning method and system based on graph search and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110604616B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111242915A (en) * | 2020-01-09 | 2020-06-05 | 北京理工大学 | Blood vessel 3D/2D registration method and device based on Monte Carlo tree search |
| CN112700551A (en) * | 2020-12-31 | 2021-04-23 | 青岛海信医疗设备股份有限公司 | Virtual choledochoscope interventional operation planning method, device, equipment and storage medium |
| CN112862786A (en) * | 2021-02-10 | 2021-05-28 | 昆明同心医联科技有限公司 | CTA image data processing method, device and storage medium |
| CN113421218A (en) * | 2021-04-16 | 2021-09-21 | 深圳大学 | Method for extracting branch point of vascular network |
| CN114027984A (en) * | 2022-01-06 | 2022-02-11 | 极限人工智能有限公司 | Tortuous blood vessel crossing control device and vascular robot system |
| CN114081625A (en) * | 2020-07-31 | 2022-02-25 | 上海微创卜算子医疗科技有限公司 | Navigation path planning method, system and readable storage medium |
| CN115690755A (en) * | 2022-10-27 | 2023-02-03 | 珠海市人民医院 | Guide wire intervention form identification method, guide wire bending potential energy overrun judgment method and intervention robot |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030208726A1 (en) * | 2002-05-03 | 2003-11-06 | Acad Corp. | Incremental cost calculation for fast wire length minimization |
| US20100180144A1 (en) * | 2009-01-15 | 2010-07-15 | International Business Machines Corporation | Power system communication management and recovery |
| CN105167849A (en) * | 2015-05-19 | 2015-12-23 | 上海大学 | Three-dimensional vascular path planning method based on ant colony algorithm |
| US20160210884A1 (en) * | 2012-01-31 | 2016-07-21 | International Business Machines Corporation | Reorganizing display of a railway timetable diagram |
| CN107276896A (en) * | 2016-11-24 | 2017-10-20 | 北京交通大学 | Improve the point-to-point transmission method for searching shortest route of Dijkstra's algorithm |
| CN107361844A (en) * | 2017-06-20 | 2017-11-21 | 上海交通大学 | A kind of safety protecting method in robot assisted cardiovascular interventional operation |
| CN109938836A (en) * | 2019-04-01 | 2019-06-28 | 上海交通大学 | A kind of automatic unmarked guidance seal wire method in blood vessel intervention robotic surgery |
-
2019
- 2019-09-10 CN CN201910853457.XA patent/CN110604616B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030208726A1 (en) * | 2002-05-03 | 2003-11-06 | Acad Corp. | Incremental cost calculation for fast wire length minimization |
| US20100180144A1 (en) * | 2009-01-15 | 2010-07-15 | International Business Machines Corporation | Power system communication management and recovery |
| US20160210884A1 (en) * | 2012-01-31 | 2016-07-21 | International Business Machines Corporation | Reorganizing display of a railway timetable diagram |
| CN105167849A (en) * | 2015-05-19 | 2015-12-23 | 上海大学 | Three-dimensional vascular path planning method based on ant colony algorithm |
| CN107276896A (en) * | 2016-11-24 | 2017-10-20 | 北京交通大学 | Improve the point-to-point transmission method for searching shortest route of Dijkstra's algorithm |
| CN107361844A (en) * | 2017-06-20 | 2017-11-21 | 上海交通大学 | A kind of safety protecting method in robot assisted cardiovascular interventional operation |
| CN109938836A (en) * | 2019-04-01 | 2019-06-28 | 上海交通大学 | A kind of automatic unmarked guidance seal wire method in blood vessel intervention robotic surgery |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111242915A (en) * | 2020-01-09 | 2020-06-05 | 北京理工大学 | Blood vessel 3D/2D registration method and device based on Monte Carlo tree search |
| CN111242915B (en) * | 2020-01-09 | 2023-08-04 | 北京理工大学 | Vascular 3D/2D registration method and device based on Monte Carlo tree search |
| CN114081625A (en) * | 2020-07-31 | 2022-02-25 | 上海微创卜算子医疗科技有限公司 | Navigation path planning method, system and readable storage medium |
| CN114081625B (en) * | 2020-07-31 | 2023-08-25 | 上海微创卜算子医疗科技有限公司 | Navigation path planning method, system and readable storage medium |
| CN112700551A (en) * | 2020-12-31 | 2021-04-23 | 青岛海信医疗设备股份有限公司 | Virtual choledochoscope interventional operation planning method, device, equipment and storage medium |
| CN112862786A (en) * | 2021-02-10 | 2021-05-28 | 昆明同心医联科技有限公司 | CTA image data processing method, device and storage medium |
| CN113421218A (en) * | 2021-04-16 | 2021-09-21 | 深圳大学 | Method for extracting branch point of vascular network |
| CN113421218B (en) * | 2021-04-16 | 2024-02-23 | 深圳大学 | Extraction method of vascular network branch point |
| CN114027984A (en) * | 2022-01-06 | 2022-02-11 | 极限人工智能有限公司 | Tortuous blood vessel crossing control device and vascular robot system |
| CN114027984B (en) * | 2022-01-06 | 2022-03-11 | 极限人工智能有限公司 | Tortuous blood vessel crossing control device and vascular robot system |
| CN115690755A (en) * | 2022-10-27 | 2023-02-03 | 珠海市人民医院 | Guide wire intervention form identification method, guide wire bending potential energy overrun judgment method and intervention robot |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110604616B (en) | 2020-12-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110604616B (en) | Interventional operation path planning method and system based on graph search and electronic equipment | |
| CN108805871B (en) | Blood vessel image processing method and device, computer equipment and storage medium | |
| WO2021213124A1 (en) | Blood flow feature prediction method and apparatus, computer device, and storage medium | |
| US9773219B2 (en) | Systems and methods for using geometry sensitivity information for guiding workflow | |
| US11847547B2 (en) | Method and system for generating a centerline for an object, and computer readable medium | |
| US10258304B1 (en) | Method and system for accurate boundary delineation of tubular structures in medical images using infinitely recurrent neural networks | |
| CN108022237B (en) | Blood vessel extraction method, system and storage medium | |
| CN109938836B (en) | Automatic unmarked guide wire guiding method in vascular intervention robot operation | |
| CN103957834A (en) | Automatic depth scrolling and orientation adjustment for semiautomated path planning | |
| CN104866585B (en) | A kind of experiment test flight data total system | |
| CN112884826A (en) | Method and device for extracting center line of blood vessel | |
| CN113033581B (en) | Bone anatomy key point positioning method in hip joint image, electronic equipment and medium | |
| US20190192096A1 (en) | Method and device for generating anatomical labels for a physiological tree structure | |
| CN111178420B (en) | Coronary artery segment marking method and system on two-dimensional contrast image | |
| Gao et al. | Adaptive zone-aware hierarchical planner for vision-language navigation | |
| CN117372661B (en) | Surgical navigation system, surgical robot system and registration method | |
| CN109949300A (en) | Method, system and the computer-readable medium of anatomical tree structure analysis | |
| CN110070529A (en) | A kind of Endovascular image division method, system and electronic equipment | |
| JP2023521188A (en) | Method and apparatus for processing vascular images based on user input | |
| US20220409309A1 (en) | Method for generating an actuation signal for a robotic system for robot-assisted navigation of a medical object and overall system | |
| CN116721072A (en) | Method, apparatus, device, medium and program product for obtaining aortic centerline | |
| US11544847B1 (en) | System and method for generating point cloud data for electro-anatomical mapping | |
| CN115147357A (en) | Automatic navigation method, device, equipment and medium for vascular intervention guide wire | |
| CN105426927A (en) | Medical image processing device, medical image processing method and medical image equipment | |
| CN108053434A (en) | A kind of support alignment method and device based on cardiovascular OCT |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |